Multi-user authentication on a device
In some implementations, a set of audio recordings capturing utterances of a user is received by a first speech-enabled device. Based on the set of audio recordings, the first speech-enabled device generates a first user voice recognition model for use in subsequently recognizing a voice of the user at the first speech-enabled device. Further, a particular user account associated with the first voice recognition model is determined, and an indication that a second speech-enabled device that is associated with the particular user account is received. In response to receiving the indication, the set of audio recordings is provided to the second speech-enabled device. Based on the set of audio recordings, the second speech-enabled device generates a second user voice recognition model for use in subsequently recognizing the voice of the user at the second speech-enabled device.
1. A computer-implemented method, comprising:
receiving, by a first speech-enabled device, a set of audio recordings capturing utterances of a user;
generating, by the first speech-enabled device and based on the set of audio recordings, a first user voice recognition model for use by the first speech-enabled device in recognizing a voice of the user in additional audio recordings subsequently received by the first speech-enabled device;
determining that the first user voice recognition model is associated with a particular user account;
receiving an indication that a second speech-enabled device is associated with the particular user account; and
in response to receiving the indication that the second speech-enabled device is associated with the particular user account:
providing the set of audio recordings to the second speech-enabled device; and
generating, by the second speech-enabled device and based on the set of audio recordings, a second user voice recognition model for use in recognizing the voice of the user in additional audio recordings subsequently received by the second speech-enabled device.
2. The method of claim 1 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that the second speech-enabled device does not already store the set of audio recordings.
3. The method of claim 1 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that a type of the first speech-enabled device matches a type of the second speech-enabled device.
4. The method of claim 1 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to:
determining, by the second speech-enabled device, that the first speech-enabled device received the set of audio recordings, and
requesting, by the second speech-enabled device, the set of audio recordings.
5. The method of claim 1 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to:
determining, by an application executing on the second speech-enabled device, that the first speech-enabled device received the set of audio recordings, and
requesting, by the application executing on second speech-enabled device, the set of audio recordings.
6. The method of claim 1 , further comprising:
prior to receiving, by the second speech-enabled device, the set of audio recordings:
determining that the second speech-enabled device does not store the set of audio recordings,
wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that the second speech-enabled device does not store the set of audio recordings.
7. The method of claim 6 , further comprising:
subsequent to generating, by the second speech-enabled device and based on the set of audio recordings, the second user voice recognition model:
receiving, by the second speech-enabled device, an additional utterance of the particular user,
determining, by the second speech-enabled device and using the second voice recognition model, that the particular user spoke the additional utterance, and
providing for audio or visual output, by the second speech-enabled device and in response to determining that the particular user spoke the additional utterance, content tailored to the particular user and responsive to the additional utterance.
8. A system, comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving, by a first speech-enabled device, a set of audio recordings capturing utterances of a user;
generating, by the first speech-enabled device and based on the set of audio recordings, a first user voice recognition model for use by the first speech-enabled device in recognizing a voice of the user in additional audio recordings subsequently received by the first speech-enabled device;
determining that the first user voice recognition model is associated with a particular user account;
receiving an indication that a second speech-enabled device is associated with the particular user account; and
in response to receiving the indication that the second speech-enabled device is associated with the particular user account:
providing the set of audio recordings to the second speech-enabled device; and
generating, by the second speech-enabled device and based on the set of audio recordings, a second user voice recognition model for use in recognizing the voice of the user in additional audio recordings subsequently received by the second speech-enabled device.
9. The system of claim 8 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to Determining that the second speech-enabled device does not already store the set of audio recordings.
10. The system of claim 8 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that a type of the first speech-enabled device matches a type of the second speech-enabled device.
11. The system of claim 8 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to:
determining, by the second speech-enabled device, that the first speech-enabled device received the set of audio recordings, and
requesting, by the second speech-enabled device, the set of audio recordings.
12. The system of claim 8 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to:
determining, by an application executing on the second speech-enabled device, that the first speech-enabled device received the set of audio recordings, and
requesting, by the application executing on second speech-enabled device, the set of audio recordings.
13. The system of claim 8 , the operations further comprising:
prior to receiving, by the second speech-enabled device, the set of audio recordings:
determining that the second speech-enabled device does not store the set of audio recordings,
wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that the second speech-enabled device does not store the set of audio recordings.
14. The system of claim 13 , the operations further comprising:
subsequent to generating, by the second speech-enabled device and based on the set of audio recordings, the second user voice recognition model:
receiving, by the second speech-enabled device, an additional utterance of the particular user,
determining, by the second speech-enabled device and using the second voice recognition model, that the particular user spoke the additional utterance, and
providing for audio or visual output, by the second speech-enabled device and in response to determining that the particular user spoke the additional utterance, content tailored to the particular user and responsive to the additional utterance.
15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
receiving, by a first speech-enabled device, a set of audio recordings capturing utterances of a user;
generating, by the first speech-enabled device and based on the set of audio recordings, a first user voice recognition model for use by the first speech-enabled device in recognizing a voice of the user in additional audio recordings subsequently received by the first speech-enabled device;
determining that the first user voice recognition model is associated with a particular user account;
receiving an indication that a second speech-enabled device is associated with the particular user account; and
in response to receiving the indication that the second speech-enabled device is associated with the particular user account:
providing the set of audio recordings to the second speech-enabled device; and
generating, by the second speech-enabled device and based on the set of audio recordings, a second user voice recognition model for use in recognizing the voice of the user in additional audio recordings subsequently received by the second speech-enabled device.
16. The non-transitory computer-readable medium of claim 15 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that the second speech-enabled device does not already store the set of audio recordings.
17. The non-transitory computer-readable medium of claim 15 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that a type of the first speech-enabled device matches a type of the second speech-enabled device.
18. The non-transitory computer-readable medium of claim 15 , wherein providing the set of audio recordings to the second speech-enabled device is performed in response to:
determining, by the second speech-enabled device, that the first speech-enabled device received the set of audio recordings, and
requesting, by the second speech-enabled device, the set of audio recordings.
19. The non-transitory computer-readable medium of claim 15 , the operations further comprising:
prior to receiving, by the second speech-enabled device, the set of audio recordings:
determining that the second speech-enabled device does not store the set of audio recordings,
wherein providing the set of audio recordings to the second speech-enabled device is performed in response to determining that the second speech-enabled device does not store the set of audio recordings.
20. The non-transitory computer-readable medium of claim 19 , the operations further comprising:
subsequent to generating, by the second speech-enabled device and based on the set of audio recordings, the second user voice recognition model:
receiving, by the second speech-enabled device, an additional utterance of the particular user,
determining, by the second speech-enabled device and using the second voice recognition model, that the particular user spoke the additional utterance, and
providing for audio or visual output, by the second speech-enabled device and in response to determining that the particular user spoke the additional utterance, content tailored to the particular user and responsive to the additional utterance.